© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 4935
    Prev
    Next
    INDEX
    Explanations

    technical details related to automobiles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and separators in lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":"/
    -0.77
    iffe
    -0.71
    Ĥİ
    -0.71
    Shape
    -0.71
    Enlarge
    -0.68
    Ń·
    -0.68
    ģĸ
    -0.66
    conom
    -0.66
    ¬¼
    -0.65
    ²¾
    -0.64
    POSITIVE LOGITS
     plus
    1.10
     lots
    1.03
     tons
    0.97
     plenty
    0.96
     etc
    0.89
     including
    0.80
     huh
    0.76
     ample
    0.75
     loads
    0.74
     followed
    0.74
    Activations Density 0.278%

    No Known Activations